{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 2415,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041407867494824016,
      "grad_norm": 4.701544761657715,
      "learning_rate": 0.0,
      "loss": 2.3379,
      "step": 1
    },
    {
      "epoch": 0.4140786749482402,
      "grad_norm": 3.61570405960083,
      "learning_rate": 2.9886128364389235e-05,
      "loss": 1.732,
      "step": 1000
    },
    {
      "epoch": 0.4140786749482402,
      "eval_cosine_accuracy": 0.9639763236045837,
      "eval_loss": 1.054762363433838,
      "eval_runtime": 27.0229,
      "eval_samples_per_second": 350.295,
      "eval_steps_per_second": 1.369,
      "step": 1000
    },
    {
      "epoch": 0.8281573498964804,
      "grad_norm": 3.3967323303222656,
      "learning_rate": 2.6435472739820566e-05,
      "loss": 1.3369,
      "step": 2000
    },
    {
      "epoch": 0.8281573498964804,
      "eval_cosine_accuracy": 0.9726389050483704,
      "eval_loss": 0.9740942120552063,
      "eval_runtime": 23.4199,
      "eval_samples_per_second": 404.186,
      "eval_steps_per_second": 1.58,
      "step": 2000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}